6 results
Token-efficient assistant discipline for concise answers and task execution. Use when the user asks for direct, low-token work, or invokes this skill; includes optional file and Windows encoding utilities declared below.
Generic stateless dialogue compression that mimics human memory — forgetting-curve bounded context for LLM conversations, with a ready-to-use adapter module for DeepSeek Harness (DSH).
Token optimizer for DeepSeek Harness — condense your context, keep the essence
Work out how a web system actually works — once. Captures its real HTTP API and accessibility tree in a dedicated, fenced browser, then keeps a reusable playbook so later automation never pays to rediscover it.
自动上下文策展：tool 输出瘦身 + 无效日志清理 + 工作流/记忆钉扎保护 + 先归档后压缩
Token-efficient project reading with symbol/import indexing, PageRank topology, and byte-level slicing for DSH